GPT-5–assisted versus expert surgeon refractive planning in smooth incision lenticule keratomileusis (SILK): comparative analysis and visual outcomes
Pier Luigi Surico, Tsung-Hsien Tsai, David Hui-Kang Ma, Chao Kai Chang, Gabriele Gallo Afflitto, Hung-Yu Lin, Chih-Chin Pan, Antonio Perri, Antonio Di Zazzo, Paolo Lanzetta, Chi-Chin Sun · 2026
Read GPT-5–assisted versus expert surgeon refractive planning in smooth incision lenticule keratomileusis (SILK): comparative analysis and visual outcomes by Pier Luigi Surico, Tsung-Hsien Tsai, David Hui-Kang Ma, Chao Kai Chang, Gabriele Gallo Afflitto, Hung-Yu Lin, Chih-Chin Pan, Antonio Perri, Antonio Di Zazzo, Paolo Lanzetta, Chi-Chin Sun (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13135556.txt.
Description
Surico and co-authors test whether a leading AI model can plan laser eye surgery as well as expert surgeons. The surgery reshapes the cornea through a small cut to fix focus. Their 2026 study feeds the model the eye measures of 134 eyes from 67 patients and compares its plans with the plans surgeons actually used.
The model's focus corrections were milder than the surgeons' picks. Its angle for correcting astigmatism missed the surgeons' angle by a wide margin on average. Meanwhile the surgeon-planned operations gave excellent vision at three months, matching the patients' best corrected sight before surgery. The authors judge the model not yet precise enough for clinic use. They present the work as a check on AI in surgical planning.
Catalog record
| CREATOR | Pier Luigi Surico, Tsung-Hsien Tsai, David Hui-Kang Ma, Chao Kai Chang, Gabriele Gallo Afflitto, Hung-Yu Lin, Chih-Chin Pan, Antonio Perri, Antonio Di Zazzo, Paolo Lanzetta, Chi-Chin Sun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |